{"url":"/dataset/pmindia","name":"PMIndia","full_name":null,"description_markdown":"Consists of parallel sentences which pair 13 major languages of India with English. The corpus includes up to 56000 sentences for each language pair.\r\n\r\nSource: [PMIndia -- A Collection of Parallel Corpora of Languages of India](/paper/pmindia-a-collection-of-parallel-corpora-of)","description_withheld":null,"homepage":"http://data.statmt.org/pmindia","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/pmindia-a-collection-of-parallel-corpora-of","title":"PMIndia -- A Collection of Parallel Corpora of Languages of India","first_author":"Barry Haddow","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["PMIndia"],"data_loaders":[],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}